使用机器学习对学习障碍和多种长期疾病的患者进行公平的住院预测
Emeka Abakasanga1, Rania Kousovista1, Georgina Cosma1
1Computer Science Department, School of Science, Loughborough University, Loughborough, United Kingdom.
Frontiers in digital health
|March 3, 2025
概括
机器学习准确地预测了学习障碍和多种长期疾病患者的住院时间. 偏见缓解技术确保跨种族群体的公平预测,改善医疗保健资源分配.
科学领域:
- 医疗保健信息学 医疗保健信息学
- 机器学习应用 机器学习应用
- 健康差距 研究 研究 研究 研究
背景情况:
- 学习障碍 (LD) 患者的死亡率更高,住院时间更长.
- 预测患有多种长期疾病 (MLTC) 的LD患者的停留时间 (LOS) 对于护理和资源管理至关重要.
- 现有的机器学习 (ML) 模型往往缺乏对敏感人群的概括性和公平性.
研究的目的:
- 开发和评估一种机器学习模型,用于预测患有LD和MLTC的患者的医院LOS.
- 针对不同种族群体的ML预测中的公平性和偏见.
- 优化医疗资源的分配,并改善对这一弱势群体的患者护理.
主要方法:
- 利用了来自威尔士9,618名LD患者的电子健康记录 (EHR).
- 开发了一个随机森林 (RF) ML模型,包括人口统计,药物,生活方式和39种长期条件.
- 应用后处理值优化和在加工中的指数梯度方法来缓解偏差.
主要成果:
- 射频模型的AUC为0.759 (男性) 和0.756 (女性).
- 偏见缓解技术减少了各族群的绩效差异,尤其是值优化器.
- 在男性队列的预测指标中观察到显著的公平性改善.
结论:
- 机器学习模型可以可行地预测LD和MLTC患者的LOS.
- 偏差缓解技术提高了医疗保健中的ML预测的公平性.
- 结果支持使用EHR数据进行公平的医疗预测,以更好地进行临床决策和资源管理.
更多相关视频
相关概念视频
Documentation in Long-Term and Home Healthcare Setting
868
Documentation in long-term care facilities and home healthcare settings is crucial for ensuring continuous, coordinated, and comprehensive care for patients. Each setting has its specific documentation processes and tools:
Long-Term Care Facilities
Long-Term Care Facilities
868
Learning Disabilities
81
Learning disabilities are cognitive disorders caused by neurological impairments that affect cognitive functions like language and reading, without indicating overall intellectual or developmental challenges. These disabilities differ from global intellectual or developmental disabilities as they are limited to distinct cognitive functions. Common learning disabilities include dysgraphia, dyslexia, and dyscalculia, each of which impacts unique aspects of learning.
Dyslexia
Dyslexia is a...
Dyslexia
Dyslexia is a...
81
Residuals and Least-Squares Property
7.2K
The vertical distance between the actual value of y and the estimated value of y. In other words, it measures the vertical distance between the actual data point and the predicted point on the line
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
If the observed data point lies above the line, the residual is positive, and the line underestimates the actual data value for y. If the observed data point lies below the line, the residual is negative, and the line overestimates the actual data value for y.
The process of fitting the best-fit...
7.2K


